PF-D2M: A Pose-free Diffusion Model for Universal Dance-to-Music Generation
This addresses the limitation of existing methods that rely on single human dancer data, improving applicability to real-world scenarios with multiple or non-human dancers.
The paper tackled the problem of generating music aligned with dance movements by proposing PF-D2M, a universal diffusion-based model that uses visual features from dance videos, achieving state-of-the-art performance in alignment and music quality.
Dance-to-music generation aims to generate music that is aligned with dance movements. Existing approaches typically rely on body motion features extracted from a single human dancer and limited dance-to-music datasets, which restrict their performance and applicability to real-world scenarios involving multiple dancers and non-human dancers. In this paper, we propose PF-D2M, a universal diffusion-based dance-to-music generation model that incorporates visual features extracted from dance videos. PF-D2M is trained with a progressive training strategy that effectively addresses data scarcity and generalization challenges. Both objective and subjective evaluations show that PF-D2M achieves state-of-the-art performance in dance-music alignment and music quality.